相关论文: Overcoming Catastrophic Forgetting by Soft Paramet…

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead…

Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains…

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…

Incrementally fine-tuning foundational models on new tasks or domains is now the de facto approach in NLP. A known pitfall of this approach is the \emph{catastrophic forgetting} of prior knowledge that happens during fine-tuning. A common…

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a…

Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter…

Catastrophe theory was originally proposed to study dynamical systems that exhibit sudden shifts in behavior arising from small changes in input. These models can generate reasonable explanation behind abrupt jumps in nonlinear dynamic…

Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount of old data stored, an intelligent system often…

In this work, we introduce a stochastic maximum principle (SMP) approach for solving the reinforcement learning problem with the assumption that the unknowns in the environment can be parameterized based on physics knowledge. For the…

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and…

Humans and most animals can learn new tasks without forgetting old ones. However, training artificial neural networks (ANNs) on new tasks typically cause it to forget previously learned tasks. This phenomenon is the result of "catastrophic…

Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network controllers (NNCs). However, their high complexity and…

Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference…

Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but…

Pre-training and fine-tuning have achieved significant advances in the information retrieval (IR). A typical approach is to fine-tune all the parameters of large-scale pre-trained models (PTMs) on downstream tasks. As the model size and the…

In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated…

Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…

Catastrophic forgetting during knowledge injection impairs the ability of large language models to acquire new knowledge without overwriting previously mastered knowledge. Recent studies analyze forgetting from a gradient similarity…

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…